GP

Llm Surgery Dark Arts Gpt Oss 60b 96a12

gpt-ossGGUF by mradermacherUpdated 2026-07-10
Download on Hugging Face
Parameters59.2B
Context128K
Layers24
Architecturegpt-oss
Smallest quant0.1 GB
Quick answer

Llm Surgery Dark Arts Gpt Oss 60b 96a12 needs about 45.4 GB of memory at Q4_K_M (a 44.5 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 25 quants, from 0.1 GB to 62.9 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

LLM Surgery Dark Arts GPT‑OSS 60B with 96 experts

LLM Surgery Dark Arts GPT‑OSS 60B is a 59.2 billion‑parameter model with a 131 072‑token context window. It is a mixture‑of‑experts architecture, expanding the expert pool while keeping the 24‑layer depth. The model is released under Apache‑2.0.

Good at

  • Reasoning
  • Tool usage
  • Large‑context handling

Limits

  • No vision support
  • Requires large VRAM for full‑precision
  • License is Apache‑2.0

Best for

  • Research on complex reasoning
  • Fine‑tuning domain‑specific models
  • Educational demonstrations

Who it’s for. Researchers and developers who need a large‑parameter, MoE model for advanced reasoning tasks. The model is suitable for fine‑tuning on specialized datasets and for exploring expert routing strategies.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.1 GB 1.0 GB
Fits Get file →
MXFP4_MOE32.5 GB 33.4 GB
Too big Get file →
IQ1_M33.6 GB 34.5 GB
Too big Get file →
IQ1_S33.6 GB 34.5 GB
Too big Get file →
IQ2_XXS33.6 GB 34.5 GB
Too big Get file →
IQ2_XS33.6 GB 34.5 GB
Too big Get file →
Q3_K_S33.6 GB 34.5 GB
Too big Get file →
IQ2_M33.6 GB 34.5 GB
Too big Get file →
IQ2_S33.6 GB 34.5 GB
Too big Get file →
IQ3_S33.6 GB 34.5 GB
Too big Get file →
IQ3_XS33.6 GB 34.5 GB
Too big Get file →
IQ3_XXS33.6 GB 34.5 GB
Too big Get file →
Q2_K33.6 GB 34.5 GB
Too big Get file →
IQ4_XS33.7 GB 34.6 GB
Too big Get file →
Q4_033.8 GB 34.7 GB
Too big Get file →
Q2_K_S33.9 GB 34.8 GB
Too big Get file →
IQ3_M34.0 GB 34.9 GB
Too big Get file →
Q3_K_M36.1 GB 37.0 GB
Too big Get file →
Q3_K_L37.3 GB 38.2 GB
Too big Get file →
Q4_137.3 GB 38.2 GB
Too big Get file →
Q4_K_S41.1 GB 42.0 GB
Too big Get file →
Q4_K_M44.5 GB 45.4 GB
Too big Get file →
Q5_K_S44.6 GB 45.5 GB
Too big Get file →
Q5_K_M47.6 GB 48.5 GB
Too big Get file →
Q6_K62.9 GB 63.8 GB
Too big Get file →

For 8 GB VRAM, use the MXFP4_MOE quant (file size 32.49 GB, memory 33.4 GB at 8 k context). For 16 GB VRAM, IQ1_M or IQ1_S (33.59 GB, 34.5 GB). For 24 GB VRAM, Q3_K_S (33.63 GB, 34.5 GB). Larger VRAM allows higher‑quality quants such as Q4_K_M (44.54 GB, 45.4 GB).

What GPU do you need for Llm Surgery Dark Arts Gpt Oss 60b 96a12?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 1.0 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_S (44.6 GB file, about 45.5 GB in use).

Which Llm Surgery Dark Arts Gpt Oss 60b 96a12 quant should you choose?

Q4_K_M is the usual starting point for Llm Surgery Dark Arts Gpt Oss 60b 96a12: it balances file size and quality well. Here it is a 44.5 GB file.

If memory is tight, the smallest file is the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters59.2B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Frequently asked questions about Llm Surgery Dark Arts Gpt Oss 60b 96a12

How much VRAM does Llm Surgery Dark Arts Gpt Oss 60b 96a12 need?

About 45.4 GB at Q4_K_M with an 8K context window. That is the 44.5 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Llm Surgery Dark Arts Gpt Oss 60b 96a12 on an 8 GB GPU?

Yes, with the smaller files: the 0.1 GB file needs about 1.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Llm Surgery Dark Arts Gpt Oss 60b 96a12 GGUF?

It depends on the quant: file is 0.1 GB, MXFP4_MOE is 32.5 GB, IQ1_M is 33.6 GB, IQ1_S is 33.6 GB, IQ2_XXS is 33.6 GB, IQ2_XS is 33.6 GB and 19 more.

What context length does Llm Surgery Dark Arts Gpt Oss 60b 96a12 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Llm Surgery Dark Arts Gpt Oss 60b 96a12 GGUF?

The files are on Hugging Face in the mradermacher/llm-surgery-dark-arts-gpt-oss-60b-96a12-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Llm Surgery Dark Arts Gpt Oss 60b 96a12 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, using the MXFP4_MOE quant which requires about 33.4 GB of VRAM at 8 k context, but you will need to reduce the context length or use a smaller quant.

Does this model support image input?

No, the model has no vision capabilities and only processes text.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of llm-surgery-dark-arts-gpt-oss-60b-96a12

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More gpt-oss models

All gpt-oss →

Other large models

All large models →